Enable Beginning-of-Sentence prediction for contextual dict.

Bug: 14161647
Bug: 14119293
Change-Id: I0c00f13966db88e4de85e245e7bced43c9d474b2

2 files changed, 26 insertions, 1 deletions

diff --git a/native/jni/src/suggest/core/session/prev_words_info.h b/native/jni/src/suggest/core/session/prev_words_info.h
index 56c53c1c2..640f6a2fc 100644
--- a/native/jni/src/suggest/core/session/prev_words_info.h
+++ b/native/jni/src/suggest/core/session/prev_words_info.h
@@ -85,6 +85,14 @@ class PrevWordsInfo {
         return mPrevWordCodePointCount[n - 1];
     }
 
+    // n is 1-indexed.
+    bool isNthPrevWordBeginningOfSentence(const int n) const {
+        if (n <= 0 || n > MAX_PREV_WORD_COUNT_FOR_N_GRAM) {
+            return false;
+        }
+        return mIsBeginningOfSentence[n - 1];
+    }
+
  private:
     DISALLOW_COPY_AND_ASSIGN(PrevWordsInfo);
 
diff --git a/native/jni/src/suggest/policyimpl/dictionary/structure/v4/ver4_patricia_trie_policy.cpp b/native/jni/src/suggest/policyimpl/dictionary/structure/v4/ver4_patricia_trie_policy.cpp
index 09c7b7d85..1e10f24c5 100644
--- a/native/jni/src/suggest/policyimpl/dictionary/structure/v4/ver4_patricia_trie_policy.cpp
+++ b/native/jni/src/suggest/policyimpl/dictionary/structure/v4/ver4_patricia_trie_policy.cpp
@@ -246,7 +246,24 @@ bool Ver4PatriciaTriePolicy::addNgramEntry(const PrevWordsInfo *const prevWordsI
             false /* tryLowerCaseSearch */);
     // TODO: Support N-gram.
     if (prevWordsPtNodePos[0] == NOT_A_DICT_POS) {
-        return false;
+        if (prevWordsInfo->isNthPrevWordBeginningOfSentence(1 /* n */)) {
+            const std::vector<UnigramProperty::ShortcutProperty> shortcuts;
+            const UnigramProperty beginningOfSentenceUnigramProperty(
+                    true /* representsBeginningOfSentence */, true /* isNotAWord */,
+                    false /* isBlacklisted */, MAX_PROBABILITY /* probability */,
+                    NOT_A_TIMESTAMP /* timestamp */, 0 /* level */, 0 /* count */, &shortcuts);
+            if (!addUnigramEntry(prevWordsInfo->getNthPrevWordCodePoints(1 /* n */),
+                    prevWordsInfo->getNthPrevWordCodePointCount(1 /* n */),
+                    &beginningOfSentenceUnigramProperty)) {
+                AKLOGE("Cannot add unigram entry for the beginning-of-sentence.");
+                return false;
+            }
+            // Refresh Terminal PtNode positions.
+            prevWordsInfo->getPrevWordsTerminalPtNodePos(this, prevWordsPtNodePos,
+                    false /* tryLowerCaseSearch */);
+        } else {
+            return false;
+        }
     }
     const int word1Pos = getTerminalPtNodePositionOfWord(
             bigramProperty->getTargetCodePoints()->data(),